# Psychological Defense Classification on PsyDefConv 2026 (official leaderboard) Source: [Psychological Defense Classification on PsyDefConv 2026 (official leaderboard)]() Collection index: [llms.txt]() Data updated: 2026-06-02T08:46:05.399Z Evaluation of Psychological Defense Classification performance on the PsyDefConv 2026 official leaderboard dataset, reporting Accuracy and Macro F1 Score. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Psychological Defense Classification | | Dataset (including any stated split) | PsyDefConv 2026 (official leaderboard) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. - [Macro F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Ministral-8B | 64.83 | Not recorded | 6a1e63c7dbd7150506f853d1 | | Qwen3-8B LoRA | 64.19 | Not recorded | 6a1e63c7dbd7150506f853d1 | | InternLM3-8B | 63.98 | Not recorded | 6a1e63c7dbd7150506f853d1 | | Llama 3.1-8B | 62.92 | Not recorded | 6a1e63c7dbd7150506f853d1 | | DeBERTa-v3-base | 59.11 | Not recorded | 6a1e63c7dbd7150506f853d1 | | Qwen3-8B LoRA | 58.43 | Not recorded | 6a1e63c7dbd7150506f853d1 | | Gemini 2.5 Pro | 56.36 | Not recorded | 6a1e63c7dbd7150506f853d1 | | DeepSeek-V3.2 | 55.72 | Not recorded | 6a1e63c7dbd7150506f853d1 | | Qwen3-8B LoRA | 54.45 | Not recorded | 6a1e63c7dbd7150506f853d1 | | GPT-5 | 52.75 | Not recorded | 6a1e63c7dbd7150506f853d1 | | RoBERTa-base | 51.27 | Not recorded | 6a1e63c7dbd7150506f853d1 | ### Ministral-8B Accuracy: 64.83. Result ID: 6a1e97bffbc373592c18d192. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"fine-tuned (SOTA)"}. This record does not assert independent reproduction. ### Qwen3-8B LoRA Accuracy: 64.19. Result ID: 6a1e97bffbc373592c18d197. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"configuration":"SeedA Ensemble + v2decode"}. This record does not assert independent reproduction. ### InternLM3-8B Accuracy: 63.98. Result ID: 6a1e97bffbc373592c18d191. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"fine-tuned"}. This record does not assert independent reproduction. ### Llama 3.1-8B Accuracy: 62.92. Result ID: 6a1e97bffbc373592c18d190. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"fine-tuned"}. This record does not assert independent reproduction. ### DeBERTa-v3-base Accuracy: 59.11. Result ID: 6a1e97bffbc373592c18d193. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"validation":"5-fold"}. This record does not assert independent reproduction. ### Qwen3-8B LoRA Accuracy: 58.43. Result ID: 6a1e97bffbc373592c18d196. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"configuration":"Grouped CV + Bias Tuning"}. This record does not assert independent reproduction. ### Gemini 2.5 Pro Accuracy: 56.36. Result ID: 6a1e97bffbc373592c18d18e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"zero-shot"}. This record does not assert independent reproduction. ### DeepSeek-V3.2 Accuracy: 55.72. Result ID: 6a1e97bffbc373592c18d18f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"zero-shot","technique":"CoT"}. This record does not assert independent reproduction. ### Qwen3-8B LoRA Accuracy: 54.45. Result ID: 6a1e97bffbc373592c18d195. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"configuration":"Baseline Finetuned"}. This record does not assert independent reproduction. ### GPT-5 Accuracy: 52.75. Result ID: 6a1e97bffbc373592c18d18d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"zero-shot","source":"task paper"}. This record does not assert independent reproduction. ### RoBERTa-base Accuracy: 51.27. Result ID: 6a1e97bffbc373592c18d194. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.